# robots.txt for airporttaxinorthampton.co.uk
# Allow Ahrefs (used for keyword tracking)
User-agent: AhrefsBot
Allow: /
Crawl-delay: 5

# Allow legitimate search engine crawlers
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Mobile
Allow: /

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /
Crawl-delay: 2

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 2

User-agent: Applebot
Allow: /
Crawl-delay: 2

# Allow AI SEARCH bots (cite your site in AI Overviews / search results)
User-agent: OAI-SearchBot
Allow: /
Crawl-delay: 2

User-agent: PerplexityBot
Allow: /
Crawl-delay: 5

# Block AI TRAINING bots
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Cohere-ai
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# Block SEO analysis and competitor tools
User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: rogerbot
Disallow: /

User-agent: Screaming Frog SEO Spider
Disallow: /

User-agent: serpstatbot
Disallow: /

# Block common scrapers
User-agent: HTTrack
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Wget
Disallow: /

User-agent: curl
Disallow: /

User-agent: libwww-perl
Disallow: /

User-agent: python-requests
Disallow: /

User-agent: python-urllib
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: Java
Disallow: /

User-agent: Go-http-client
Disallow: /

# Block headless browsers
User-agent: HeadlessChrome
Disallow: /

User-agent: PhantomJS
Disallow: /

# Block aggressive bots
User-agent: PetalBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: Sogou
Disallow: /

User-agent: 360Spider
Disallow: /

# Default rule for all other bots
User-agent: *
Disallow: /wp-admin
Disallow: /admin
Disallow: /staff
Disallow: /.env
Disallow: /config
Disallow: /data/
Disallow: /api/
Disallow: /portal/
Allow: /api/locations
Allow: /api/quote
Crawl-delay: 10
Disallow: /staff/

# Sitemap location
Sitemap: https://www.airporttaxinorthampton.co.uk/sitemap.xml
Sitemap: https://www.airporttaxinorthampton.co.uk/sitemap-venues.xml